Ahmet Benzer

abenzerps's activity

• All
• Models
• Datasets
• Spaces
• Buckets
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

New activity in abenzerps/Qwen-Image-2.1-GGUF about 15 hours ago

what i did wrong

9

#13 opened about 15 hours ago by

D1m0n4ik

vae & clip

➕ 1

4

#11 opened about 22 hours ago by

yakasantera

New activity in abenzerps/Qwen-Image-2.1-GGUF about 16 hours ago

request

➕ 1

1

#12 opened about 16 hours ago by

Merhabalar

New activity in abenzerps/Qwen-Image-2.1-GGUF about 18 hours ago

What do you mean by uncensored?

8

#5 opened 1 day ago by

SoloMolo

New activity in abenzerps/Qwen-Image-2.1-GGUF about 22 hours ago

AMD GPU Performance Is Poor

➕ 1

1

#10 opened about 22 hours ago by

ft5191306

New activity in abenzerps/Qwen-Image-2.1-GGUF about 23 hours ago

136 or 128

5

#9 opened about 23 hours ago by

Amirmansour77

New activity in abenzerps/Qwen-Image-2.1-GGUF about 24 hours ago

🚩🚩🚩🚩 this model is not Uncensored at all, he is lying, its just the same original quants

👍 7

7

#7 opened 1 day ago by

JoshYuri

New activity in abenzerps/Qwen-Image-2.1-GGUF 1 day ago

Q6_K --> ValueError: This model is not currently supported - (Unknown model architecture!)

➕ 1

2

#6 opened 1 day ago by

lucientergal

A different Error with KSampler: "Expected weight to be of same shape as normalized_shape, but got weight of shape [136] and normalized_shape = [128]"

➕ 1

12

#4 opened 1 day ago by

minchin

I get a error

➕ 3

1

#1 opened 1 day ago by

santaonholidays

Request: DOI

➕ 1

2

#2 opened 1 day ago by

x1211

New activity in 0xSojalSec/Qwen-Image-2.1-Uncensored-GGUF 1 day ago

🚩 Report: Copyright infringement

#1 opened 1 day ago by

abenzerps

New activity in abenzerps/Nex-N2.5-mini-GGUF 7 days ago

TQ1 is producing gibberish

1

#1 opened 8 days ago by

ProgrammerV100

New activity in abenzerps/Spark-X2.5-4B-MLX-8bit 11 days ago

HELP! Why I Can't use this model in oMLX v0.6.4

➕ 1

1

#1 opened 11 days ago by

palmnovel

New activity in abenzerps/Spark-X2.5-4B-GGUF 13 days ago

6 bit version is best for programming tasks but thinks way too much.

➕ 1

1

#2 opened 13 days ago by

DPS-900

New activity in abenzerps/MiniCPM5-2B-GGUF 13 days ago

Overthinking

➕ 1

1

#1 opened 13 days ago by

budkovsky

New activity in abenzerps/Spark-X2.5-4B-GGUF 15 days ago

Do you need to compile llama.cpp to run this?

➕ 1

5

#1 opened 16 days ago by

sa13ma

New activity in abenzerps/K2-Horizon-MoVA-36B-A4B-MLX-4bit 16 days ago

Not much success so far

#1 opened 17 days ago by

ajayre

New activity in abenzerps/K2-Horizon-MoVA-36B-A4B-GGUF 19 days ago

chat_template.jinja not compatible with llama.cpp's jinja parser, also --cpu-moe doesn't seem to work you have to force -ot "exps=CPU"

➕ 1

1

#2 opened 19 days ago by

Tibbnak

no llama.cpp

➕ 1

5

#1 opened 19 days ago by

mpieck